Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add stepanov1975/hermes-local-knowledge --skill local-knowledge-routergit clone --depth 1 https://github.com/stepanov1975/hermes-local-knowledgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/stepanov1975/hermes-local-knowledge/local-knowledge-router)<a href="https://agentmods.dev/skills/stepanov1975/hermes-local-knowledge/local-knowledge-router"><img src="https://agentmods.dev/badge/skills/stepanov1975/hermes-local-knowledge/local-knowledge-router/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stepanov1975/hermes-local-knowledge/local-knowledge-router"><img src="https://agentmods.dev/badge/skills/stepanov1975/hermes-local-knowledge/local-knowledge-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00877 |
| Opus 5 | $0.00017 | $0.00439 |
| Sonnet 5 | $0.00007 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
local-knowledge-router scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to local-knowledge-router — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Knowledge Router
When to use
Use this skill before guessing paths or doing broad file searches when a user asks about local or private operational knowledge, including:
- installed or custom Hermes skills and their support docs;
- generated tool OKFs, runbooks, operational docs, and memory docs;
- helper scripts and automation entry points;
- cron jobs and scheduled maintenance;
- MCP servers and wrapper scripts;
- service workflows in the configured local source tree.
The plugin indexes whole artifacts. It identifies the first artifact to inspect; it does not replace reading that source.
Workflow
-
Search for the user's intent:
knowledge_search(query="backup runbook", limit=8) knowledge_search(query="paperless review automation", limit=8) knowledge_search(query="siyuan mcp wrapper", limit=8) -
Fetch the best artifact before acting:
knowledge_get(artifact_id="skill:example-skill", include_neighbors=true)Use
knowledge_neighborsseparately when graph context will help:knowledge_neighbors(artifact_id="cron:daily-review", limit=20) -
Inspect the routed source of truth:
skill→ load it withskill_view.script→ read the script and help text before running it.tool_okf→ use it as routing context, then inspect the live tool schema/docs before high-impact calls.runbook,memory_doc,doc, orskill_support_doc→ read the file before changing systems.cron_job→ verify the live cron registry before mutating jobs.mcp_server→ inspect the live wrapper/config before troubleshooting.
-
Check freshness when it matters. Managed lookups rebuild an index that is missing, corrupt, older-format, or marked dirty by completed tool-OKF publication. They do not detect ordinary source-file, cron-registry, or MCP-config changes. When those changed recently or results look stale, force a rebuild:
knowledge_search(query="new helper script", limit=8, rebuild=true)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed 1b9b8e2236b8
- 9d ago First seen · 83 lines · 35 tokens per session scan A 5cb94911702c
local-knowledge-router is a skill published in the GitHub repository stepanov1975/hermes-local-knowledge (8 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 877 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to local-knowledge-router, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
mental-model-updater
Activate mental-model-updater when new insights, experiences, or experimental results need to be integrated into existing mental models, skills, or knowledge structures. Focus on synthesis, updating assumptions, and reducing outdated beliefs. Works closely with self-improver and experimenter. Triggered by mental model…
distilly
Build and use evidence-grounded local person profiles with Distilly's exact five-tool workflow. Use when a user asks to research, ingest, distill, update, correct, retrieve, or recall a real or fictional person's profile, voice, boundaries, or evidence.
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
hermes-context-optimization
Use this when the user asks about Hermes prompt/context size, “hello” startup cost, compression behavior, memory/profile bloat, tool-schema overhead, skill loading, session-store/search-index storage, or multimodal/visual-context approaches such as Snapcompact.